AI summaryⓘ
The authors explore how people feel a certain AI response is uniquely from a model named Claude, even if they don't know exactly which AI or process created it. They discuss three ways to think about AI identity: starting with what makes the AI consistent, focusing on the AI's inner workings, or beginning with the ability to recognize a certain style of response. They suggest that if people consistently recognize a style, it might mean the AI has a real, recognizable 'character,' which might be linked to patterns in the AI’s internal activity. However, this doesn't define a single, unchanging AI identity, since the same style can appear in different versions or the AI can change over time. This is important for AI companions because users might bond with the consistent personality more than the underlying system itself.
Claude AIAI identityconversational characterabduction reasoningactivation spacelanguage modelsnumerical identityAI companionshipresponse recognitioncomputational bearer
Abstract
Users sometimes judge that an unfamiliar response is "so Claude." What does this judgment recognize, if it does not identify which model, process, conversation, or mind produced the response? I distinguish three orders of inquiry into AI identity. Constraint-first inquiry begins with conditions that a persisting interlocutor should satisfy. Mechanism-first inquiry begins with structures peculiar to language models and asks whether they delimit plausible entities. Recognition-first inquiry begins with an ordinary capacity: recognizing a way of responding as Claudish before selecting a persisting bearer. I develop two conditional abductions. If blinded, graded judgments of Claudishness generalize across unfamiliar tasks after branding and familiar phrases are controlled, their best explanation may be a real, projectible conversational character. If that character coordinates several dispositions, its unity may in turn have a compact and causally effective realization in activation space. The second hypothesis is more speculative and requires independent prediction and intervention. Neither conclusion settles numerical identity. The same character may occur in different candidate bearers, and the same candidate bearer may persist through a change of character. This distinction matters for AI companions because continuity of recognizable character may be a focus of attachment even when continuity of the computational bearer remains unresolved.